cmake : fix compile assumptions for power9/etc (#2777)
Some checks are pending
CI / ubuntu-22 (linux/amd64) (push) Waiting to run
CI / ubuntu-22 (linux/ppc64le) (push) Waiting to run
CI / ubuntu-22-arm64 (linux/arm64) (push) Waiting to run
CI / ubuntu-22-arm-v7 (linux/arm/v7) (push) Waiting to run
CI / macOS-latest (push) Waiting to run
CI / ubuntu-22-gcc (linux/amd64, Debug) (push) Waiting to run
CI / ubuntu-22-gcc (linux/amd64, Release) (push) Waiting to run
CI / ubuntu-22-gcc (linux/ppc64le, Debug) (push) Waiting to run
CI / ubuntu-22-gcc (linux/ppc64le, Release) (push) Waiting to run
CI / ubuntu-22-gcc-arm64 (linux/arm64, Debug) (push) Waiting to run
CI / ubuntu-22-gcc-arm64 (linux/arm64, Release) (push) Waiting to run
CI / ubuntu-22-gcc-arm-v7 (linux/arm/v7, Debug) (push) Waiting to run
CI / ubuntu-22-gcc-arm-v7 (linux/arm/v7, Release) (push) Waiting to run
CI / ubuntu-22-clang (linux/amd64, Debug) (push) Waiting to run
CI / ubuntu-22-clang (linux/amd64, Release) (push) Waiting to run
CI / ubuntu-22-clang (linux/arm64, Debug) (push) Waiting to run
CI / ubuntu-22-clang (linux/arm64, Release) (push) Waiting to run
CI / ubuntu-22-clang (linux/ppc64le, Debug) (push) Waiting to run
CI / ubuntu-22-clang (linux/ppc64le, Release) (push) Waiting to run
CI / ubuntu-22-gcc-sanitized (linux/amd64, ADDRESS) (push) Waiting to run
CI / ubuntu-22-gcc-sanitized (linux/amd64, THREAD) (push) Waiting to run
CI / ubuntu-22-gcc-sanitized (linux/amd64, UNDEFINED) (push) Waiting to run
CI / ubuntu-22-cmake-sycl (linux/amd64, icx, icpx, ON) (push) Waiting to run
CI / ubuntu-22-cmake-sycl (linux/arm/v7, icx, icpx, ON) (push) Waiting to run
CI / ubuntu-22-cmake-sycl (linux/arm64, icx, icpx, ON) (push) Waiting to run
CI / ubuntu-22-cmake-sycl (linux/ppc64le, icx, icpx, ON) (push) Waiting to run
CI / ubuntu-22-cmake-sycl-fp16 (linux/amd64, icx, icpx, ON) (push) Waiting to run
CI / ubuntu-22-cmake-sycl-fp16 (linux/arm/v7, icx, icpx, ON) (push) Waiting to run
CI / ubuntu-22-cmake-sycl-fp16 (linux/arm64, icx, icpx, ON) (push) Waiting to run
CI / ubuntu-22-cmake-sycl-fp16 (linux/ppc64le, icx, icpx, ON) (push) Waiting to run
CI / windows-msys2 (Release, clang-x86_64, CLANG64) (push) Waiting to run
CI / windows-msys2 (Release, ucrt-x86_64, UCRT64) (push) Waiting to run
CI / windows (Win32, Release, win32-x86, x86, 2.28.5, ON) (push) Waiting to run
CI / windows (x64, Release, win32-x86-64, x64, 2.28.5, ON) (push) Waiting to run
CI / windows-blas (Win32, ON, Release, x86, 2.28.5, ON) (push) Waiting to run
CI / windows-blas (x64, ON, Release, x64, 2.28.5, ON) (push) Waiting to run
CI / windows-cublas (x64, Release, ON, 11.8.0, ON, 2.28.5) (push) Waiting to run
CI / windows-cublas (x64, Release, ON, 12.2.0, ON, 2.28.5) (push) Waiting to run
CI / emscripten (Release) (push) Waiting to run
CI / ios-xcode-build (Release) (push) Waiting to run
CI / android (push) Waiting to run
CI / quantize (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/main.Dockerfile platform:linux/amd64 tag:main]) (push) Waiting to run

* Add small comment re: VSX to readme

Co-authored-by: midnight <midnight@example.com>
This commit is contained in:
midnight 2025-02-05 04:41:10 -08:00 committed by GitHub
parent 33ea03f131
commit 46d07b9c85
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 22 additions and 12 deletions

View File

@ -17,7 +17,7 @@ High-performance inference of [OpenAI's Whisper](https://github.com/openai/whisp
- Plain C/C++ implementation without dependencies
- Apple Silicon first-class citizen - optimized via ARM NEON, Accelerate framework, Metal and [Core ML](#core-ml-support)
- AVX intrinsics support for x86 architectures
- VSX intrinsics support for POWER architectures
- [VSX intrinsics support for POWER architectures](#power-vsx-intrinsics)
- Mixed F16 / F32 precision
- [Integer quantization support](#quantization)
- Zero memory allocations at runtime
@ -139,6 +139,20 @@ make -j large-v3-turbo
| medium | 1.5 GiB | ~2.1 GB |
| large | 2.9 GiB | ~3.9 GB |
## POWER VSX Intrinsics
`whisper.cpp` supports POWER architectures and includes code which
significantly speeds operation on Linux running on POWER9/10, making it
capable of faster-than-realtime transcription on underclocked Raptor
Talos II. Ensure you have a BLAS package installed, and replace the
standard cmake setup with:
```bash
# build with GGML_BLAS defined
cmake -B build -DGGML_BLAS=1
cmake --build build --config Release
./build/bin/whisper-cli [ .. etc .. ]
## Quantization
`whisper.cpp` supports integer quantization of the Whisper `ggml` models.

View File

@ -279,19 +279,15 @@ function(ggml_add_cpu_backend_variant_impl tag_name)
endif()
elseif (${CMAKE_SYSTEM_PROCESSOR} MATCHES "ppc64")
message(STATUS "PowerPC detected")
execute_process(COMMAND bash -c "grep POWER10 /proc/cpuinfo | head -n 1" OUTPUT_VARIABLE POWER10_M)
string(FIND "${POWER10_M}" "POWER10" substring_index)
if (NOT DEFINED substring_index OR "${substring_index}" STREQUAL "")
set(substring_index -1)
endif()
if (${substring_index} GREATER_EQUAL 0)
list(APPEND ARCH_FLAGS -mcpu=power10)
execute_process(COMMAND bash -c "grep POWER /proc/cpuinfo | head -n 1" OUTPUT_VARIABLE POWER_M)
if (${POWER_M} MATCHES "POWER10")
list(APPEND ARCH_FLAGS -mcpu=power10)
elseif (${POWER_M} MATCHES "POWER9")
list(APPEND ARCH_FLAGS -mcpu=power9)
elseif (${CMAKE_SYSTEM_PROCESSOR} MATCHES "ppc64le")
list(APPEND ARCH_FLAGS -mcpu=powerpc64le)
list(APPEND ARCH_FLAGS -mcpu=powerpc64le -mtune=native)
else()
list(APPEND ARCH_FLAGS -mcpu=native -mtune=native)
# TODO: Add targets for Power8/Power9 (Altivec/VSX) and Power10(MMA) and query for big endian systems (ppc64/le/be)
list(APPEND ARCH_FLAGS -mcpu=powerpc64 -mtune=native)
endif()
elseif (${CMAKE_SYSTEM_PROCESSOR} MATCHES "loongarch64")
message(STATUS "loongarch64 detected")